Versatile Recompression-Aware Perceptual Image Super-Resolution
This addresses a practical issue for image processing applications where SR outputs are recompressed, offering incremental improvements in efficiency.
The paper tackles the problem of perceptual image super-resolution (SR) outputs being degraded by recompression for storage and transmission, and presents VRPSR, which makes SR aware of versatile compression, saving over 10% bitrate based on Real-ESRGAN and S3Diff under H.264/H.265/H.266 compression.
Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission. Ignoring recompression is suboptimal as the downstream codec might add additional artifacts to restored images. However, jointly optimizing SR and recompression is challenging, as the codecs are not differentiable and vary in configuration. In this paper, we present Versatile Recompression-Aware Perceptual Super-Resolution (VRPSR), which makes existing perceptual SR aware of versatile compression. First, we formulate compression as conditional text-to-image generation and utilize a pre-trained diffusion model to build a generalizable codec simulator. Next, we propose a set of training techniques tailored for perceptual SR, including optimizing the simulator using perceptual targets and adopting slightly compressed images as the training target. Empirically, our VRPSR saves more than 10\% bitrate based on Real-ESRGAN and S3Diff under H.264/H.265/H.266 compression. Besides, our VRPSR facilitates joint optimization of the SR and post-processing model after recompression.